syhw
commited on
Commit
•
b15aea0
1
Parent(s):
5c52af7
Update README.md
Browse filesadded line on dataset source (licensed data)
README.md
CHANGED
|
@@ -21,6 +21,8 @@ Check out our [sample page][musicgen_samples] or test the available demo!
|
|
| 21 |
</a>
|
| 22 |
<br>
|
| 23 |
|
|
|
|
|
|
|
| 24 |
## Installation
|
| 25 |
Audiocraft requires Python 3.9, PyTorch 2.0.0, and a GPU with at least 16 GB of memory (for the medium-sized model). To install Audiocraft, you can run the following:
|
| 26 |
|
|
|
|
| 21 |
</a>
|
| 22 |
<br>
|
| 23 |
|
| 24 |
+
We use 20K hours of licensed music to train MUSICGEN. Specifically, we rely on an internal dataset of 10K high-quality music tracks, and on the ShutterStock and Pond5 music data.
|
| 25 |
+
|
| 26 |
## Installation
|
| 27 |
Audiocraft requires Python 3.9, PyTorch 2.0.0, and a GPU with at least 16 GB of memory (for the medium-sized model). To install Audiocraft, you can run the following:
|
| 28 |
|